Research Engineer: AI Safety & Alignment

Aisi; Greater London; Hybrid; GBP 65,000 - 115,000; Full time

Benefits offered by this job

Hybrid working

25 days annual leave

Pension contributions

Job summary

AI Security Institute seeks Research Engineers and Research Scientists to join the Alignment Red Team in London. We hire at junior, senior, staff and principal levels, focusing on misalignment risks, evaluation methodologies, and tooling for frontier AI systems.

The team conducts pre-deployment testing, analyzes results, and shares findings with frontier labs, industry and government partners. Hybrid work and strong research drive are encouraged.

Qualifications

• Ability to work autonomously on complex research projects involving substantial engineering.
• Strong software engineering and ML experience with language models.
• Proven experience writing clean, documented research code for ML experiments.

Responsibilities

• Research methods to automatically search for misalignment in frontier models.
• Build and run alignment evaluations for loss-of-control risks.
• Conduct pre-deployment evaluations and report results to frontier AI companies and governments.
• Contribute to public-facing research publications and technical reports.
• Design and build software/tools, including open-source, for alignment evaluations.

Skills

Python for ML

ML engineering

PyTorch

Research coding

Team collaboration

Tools

Inspect

Job description

AI Security Institute seeks Research Engineers and Research Scientists to join the Alignment Red Team in London. We hire at junior, senior, staff and principal levels, focusing on misalignment risks, evaluation methodologies, and tooling for frontier AI systems.

The team conducts pre-deployment testing, analyzes results, and shares findings with frontier labs, industry and government partners. Hybrid work and strong research drive are encouraged.